Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amente
    -0.06
     circumstance
    -0.06
    loit
    -0.06
    عات
    -0.06
    (play
    -0.06
    cing
    -0.06
    Album
    -0.06
    、あ
    -0.06
    ُل
    -0.06
    ption
    -0.06
    POSITIVE LOGITS
     μεγ
    0.07
     السعودية
    0.07
     وب
    0.07
     BaseType
    0.06
    Michael
    0.06
     disappointed
    0.06
     مهند
    0.06
    .selection
    0.06
    itbart
    0.06
    33
    0.06
    Act Density 0.024%

    No Known Activations